首页|AUTOMATIC DETECTION OF TUBERCULOSIS BACTERIA USING MICROSCOPE IMAGING SYSTEM BASED ON MOTORIZED SERVO AND DEEP LEARNING TECHNIQUES
AUTOMATIC DETECTION OF TUBERCULOSIS BACTERIA USING MICROSCOPE IMAGING SYSTEM BASED ON MOTORIZED SERVO AND DEEP LEARNING TECHNIQUES
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
This research presents an automated system for detecting tuberculosis bacteria in sputum samples using deep learning. The study primarily focuses on developing a detection algorithm based on the Y0L0v8 architecture to accurately identify tuberculosis bacteria. The system integrates a computer, camera, and microcontroller to automate the movement of preparation and focus servos for enhanced scanning efficiency. Performance testing of the microscope-robot system reveals a precision rate of 81.28% and a recall of 90.71%, demonstrating a balanced performance. The precision-confidence curve shows high confidence in classifying positive samples, while the recall-confidence analysis indicates the model's strong ability to identify true positives. Despite the 75.1% overall accuracy, there are some false positives and false negatives. The system holds promise for accelerating and improving tuberculosis detection. Future work will focus on refining the model to enhance accuracy and overcome existing limitations. This research contributes to the development of faster, more reliable diagnostic technology for tuberculosis detection in medical settings.
Tuberculosis detectionDeep learningAutomated systemYOLOv8 model
Department of Information and Computer Engineering Electronic Engineering Polytechnic Institute of Surabaya Jl. Raya ITS, Keputih, Sukolilo, Surabaya 60111, Indonesia
KSM Clinical Microbiology Dr. Soetomo Hospital Medical Teaching Department of Medical Microbiology Faculty of Medicine Universitas Airlangga Jl. Prof. DR. Moestopo No. 47, Surabaya, Jawa Timur 60132, Indonesia
Ministry of Manpower Jl. Jendral Gatot Subroto Kav. 51 Jakarta Selatan, Jakarta 12750, Indonesia
NETL
NSTL
